Search Results for author:
Found 103 papers, 40 papers with code
Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting.
Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting
Recurring concept drift, a type of concept drift in which previously observed data patterns reappear after some time, is one of the most prevalent types of concept drift in time series.
Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond
In contrast to existing methods that rely on adjusting model parameters, MFL leverages a lightweight reverse model to iteratively search for optimal inputs, enabling efficient adaptation to new objectives under deployment constraints.
T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models
Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains.
Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey
Spatio-Temporal (ST) data science, which includes sensing, managing, and mining large-scale data across space and time, is fundamental to understanding complex systems in domains such as urban computing, climate science, and intelligent transportation.
Backtracking for Safety
Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial.
Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions.
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement
Time series data are foundational in finance, healthcare, and energy domains.
TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation
Based on this observation, we introduce TimeDistill, a cross-architecture KD framework that transfers these patterns from teacher models (e. g., Transformers, CNNs) to MLP.
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy.
Position: Empowering Time Series Reasoning with Multimodal LLMs
Understanding time series data is crucial for multiple real-world applications.
Detecting Zero-Day Attacks in Digital Substations via In-Context Learning
The occurrences of cyber attacks on the power grids have been increasing every year, with novel attack techniques emerging every year.
LLMs Can Plan Only If We Tell Them
Large language models (LLMs) have demonstrated significant capabilities in natural language processing and reasoning, yet their effectiveness in autonomous planning has been under debate.
Rethinking Hardware Impairments in Multi-User Systems: Can FAS Make a Difference?
In this paper, we analyze the role of fluid antenna systems (FAS) in multi-user systems with hardware impairments (HIs).
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
Driven by these concerns, machine unlearning has become crucial to effectively purge undesirable knowledge from models.
Augmenting Minds or Automating Skills: The Differential Role of Human Capital in Generative AI's Impact on Creative Tasks
This framework elucidates how AI shifts the locus of creative advantage from specialized expertise to broader cognitive adaptability.
FAS for Secure and Covert Communications
This letter considers a fluid antenna system (FAS)-aided secure and covert communication system, where the transmitter adjusts multiple fluid antennas' positions to achieve secure and covert transmission under the threat of an eavesdropper and the detection of a warden.
FAS-Driven Spectrum Sensing for Cognitive Radio Networks
Cognitive radio (CR) networks face significant challenges in spectrum sensing, especially under spectrum scarcity.
EffiCANet: Efficient Time Series Forecasting with Convolutional Attention
The exponential growth of multivariate time series data from sensor networks in domains like industrial monitoring and smart cities requires efficient and accurate forecasting models.
Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications.
TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis
Specifically, we introduce a general-purpose TSPM that processes multi-scale time series using (1) multi-resolution time imaging (MRTI), (2) time image decomposition (TID), (3) multi-scale mixing (MCM), and (4) multi-resolution mixing (MRM) to extract comprehensive temporal patterns.
Towards Neural Scaling Laws for Time Series Foundation Models
In this work, we examine two common TSFM architectures, encoder-only and decoder-only Transformers, and investigate their scaling behavior on both ID and OOD data.
EvoFA: Evolvable Fast Adaptation for EEG Emotion Recognition
While numerous domain adaptation (DA) approaches have been proposed in recent years to address this issue, their reliance on large amounts of target data for calibration restricts them to offline scenarios, rendering them unsuitable for real-time applications.
Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications.
BCRLB Under the Fusion Extended Kalman Filter
However, the data measured by radar nodes contains noise, clutter, and false targets, making it difficult for the fusion center to directly establish the association between radar measurements and real targets.
Towards Universal Large-Scale Foundational Model for Natural Gas Demand Forecasting
In the context of global energy strategy, accurate natural gas demand forecasting is crucial for ensuring efficient resource allocation and operational planning.
DiPT: Enhancing LLM reasoning through diversified perspective-taking
This approach allows the model to gain a deeper understanding of the problem's context and identify the most effective solution path during the inference stage.
Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning
Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation.
FAS-RIS Communication: Model, Analysis, and Optimization
This correspondence investigates the novel fluid antenna system (FAS) technology, combining with reconfigurable intelligent surface (RIS) for wireless communications, where a base station (BS) communicates with a FAS-enabled user with the assistance of a RIS.
Full-Duplex ISAC-Enabled D2D Underlaid Cellular Networks: Joint Transceiver Beamforming and Power Allocation
Integrating device-to-device (D2D) communication into cellular networks can significantly reduce the transmission burden on base stations (BSs).
FAS vs. ARIS: Which Is More Important for FAS-ARIS Communication Systems?
We introduce an alternating optimization (AO) algorithm incorporating majorization-minimization (MM), successive convex approximation (SCA), and sequential rank-one constraint relaxation (SRCR) to tackle the non-convex challenges inherent in these systems.
DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
Dynamic graph learning aims to uncover evolutionary laws in real-world systems, enabling accurate social recommendation (link prediction) or early detection of cancer cells (classification).
A Hypothesis on Black Swan in Unchanging Environments
Black swan events are statistically rare occurrences that carry extremely high risks.
Data-Centric Human Preference Optimization with Rationales
Reinforcement learning from human feedback plays a crucial role in aligning language models towards human preferences, traditionally represented through comparisons between pairs or sets of responses within a given context.
Fluid Antenna-Assisted Simultaneous Wireless Information and Power Transfer Systems
Unlike traditional SWIPT systems with fixed-position antennas (FPAs), our FA-assisted system enables dynamic reconfiguration of the radio propagation environment by adjusting the positions of FAs.
A Framework of FAS-RIS Systems: Performance Analysis and Throughput Optimization
Then, to address the possible high computational complexity in the gradient algorithm, we approximate the objective function and confirm a unique optimal solution accessible through a bisection search method.
Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?
Text summarization, a key natural language generation (NLG) task, is vital in various domains.
InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States
Despite their vast capabilities, Large Language Models (LLMs) often struggle with generating reliable outputs, frequently producing high-confidence inaccuracies known as hallucinations.
Fairness-Aware Meta-Learning via Nash Bargaining
To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set.
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints.
A CMDP-within-online framework for Meta-Safe Reinforcement Learning
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience.
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints.
Multi-Objective Reinforcement Learning
reinforcement-learning
+1
Pausing Policy Learning in Non-stationary Reinforcement Learning
Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from the past, updates the decision model in the present, and deploys it in the future.
Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering.
Preparing for Black Swans: The Antifragility Imperative for Machine Learning
Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications.
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications.
A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.
Foundation Models for Time Series Analysis: A Tutorial and Survey
Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications.
Joint Optimization for Achieving Covertness in MIMO Over-the-Air Computation Networks
This paper investigates covert data transmission within a multiple-input multiple-output (MIMO) over-the-air computation (AirComp) network, where sensors transmit data to the access point (AP) while guaranteeing covertness to the warden (Willie).
TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to the self-instruct paradigm.
Exploring Fairness for FAS-assisted Communication Systems: from NOMA to OMA
This paper addresses the fairness issue within fluid antenna system (FAS)-assisted non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) systems, where a single fixed-antenna base station (BS) transmits superposition-coded signals to two users, each with a single fluid antenna.
Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
In long-term time series forecasting (LTSF) tasks, an increasing number of models have acknowledged that discrete time series originate from continuous dynamic systems and have attempted to model their dynamical structures.
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes
Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point.
Position: What Can Large Language Models Tell Us about Time Series Analysis
Time series analysis is essential for comprehending the complexities inherent in various realworld systems and applications.
Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values
However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values.
HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling for Long-Term Forecasting
Time series forecasting is crucial and challenging in the real world.
Ranked #18 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space
Domain generalization focuses on leveraging knowledge from multiple related domains with ample training data and labels to enhance inference on unseen in-distribution (IN) and out-of-distribution (OOD) domains.
Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook
In this survey, we offer a comprehensive and up-to-date review of large models tailored (or adapted) for time series and spatio-temporal data, spanning four key facets: data types, model categories, model scopes, and application areas/tasks.
Proactive Monitoring via Jamming in Fluid Antenna Systems
Our objective is to maximize the average monitoring rate, whose expression involves the integral of the first-order Marcum $Q$ function.
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
We begin by reprogramming the input time series with text prototypes before feeding it into the frozen LLM to align the two modalities.
Ranked #1 on
Time Series Forecasting
on ETTh1 (48)
Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study
Furthermore, our enhanced attacks outperform the baseline across multiple models and datasets, with the weakly supervised attack demonstrating an average-case performance improvement of $17\%$ and being at least $7$X more effective at low false-positive rates.
Tempo Adaptation in Non-stationary Reinforcement Learning
In the context of the time-desynchronized environment, however, the agent at time $t_{k}$ allocates $\Delta t$ for trajectory generation and training, subsequently moves to the next episode at $t_{k+1}=t_{k}+\Delta t$.
Message Passing Based Block Sparse Signal Recovery for DOA Estimation Using Large Arrays
This work deals with directional of arrival (DOA) estimation with a large antenna array.
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning capacities.
A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability
This paper outlines a natural conversational approach to solving personalized energy-related problems using large language models (LLMs).
WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine
We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain.
Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection
To overcome these limitations, we propose a novel method, correlation-aware spatial-temporal graph learning (termed CST-GL), for time series anomaly detection.
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection
In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation.
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
To fill this gap, we review current state-of-the-art SSL methods for time series data in this article.
Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
To better comprehend the complex physical laws, this paper proposes a novel learning based simulation model- Graph Networks with Spatial-Temporal neural Ordinary Equations (GNSTODE)- that characterizes the varying spatial and temporal dependencies in particle systems using a united end-to-end framework.
How Expressive are Spectral-Temporal Graph Neural Networks for Time Series Forecasting?
In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs.
LAVA: Data Valuation without Pre-Specified Learning Algorithms
(1) We develop a proxy for the validation performance associated with a training set based on a non-conventional class-wise Wasserstein distance between training and validation sets.
Geometric Relational Embeddings: A Survey
Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions.
Hierarchical Multi-label Classification
Knowledge Graph Completion
+3
IP-FL: Incentivized and Personalized Federated Learning
Our approach enhances the personalized model appeal for self-aware clients with high-quality data leading to their active and consistent participation.
Monte Carlo Grid Dynamic Programming: Almost Sure Convergence and Probability Constraints
This paper presents a Monte Carlo-based sampling approach for the state space and an interpolation procedure for the resulting value function, dependent on the process noise density, in a "self-approximating" fashion, eliminating the need for ordering or set-membership tests.
Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance
Modern power systems will have to face difficult challenges in the years to come: frequent blackouts in urban areas caused by high power demand peaks, grid instability exacerbated by intermittent renewable generation, and global climate change amplified by rising carbon emissions.
On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds
We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension.
Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, and Separation Design
We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs).
Hyper-Parameter Auto-Tuning for Sparse Bayesian Learning
Choosing the values of hyper-parameters in sparse Bayesian learning (SBL) can significantly impact performance.
Recognizing Nested Entities from Flat Supervision: A New NER Subtask, Feasibility and Challenges
However, existing nested NER models heavily rely on training data annotated with nested entities, while labeling such data is costly.
Variational Bayesian Inference Clustering Based Joint User Activity and Data Detection for Grant-Free Random Access in mMTC
Furthermore, in conjunction with the AMP algorithm, a variational Bayesian inference based clustering (VBIC) algorithm is developed to solve this clustering problem.
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
Most poisoning defenses presume access to a set of clean data (or base set).
Learning Neural Networks under Input-Output Specifications
In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors.
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction.
From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach
Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce.
Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
To overcome the aforementioned problems, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme.
Adversarial Unlearning of Backdoors via Implicit Hypergradient
Particularly, its performance is more robust to the variation on triggers, attack settings, poison ratio, and clean data size.
Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs
Spatiotemporal representation learning on multivariate time series has received tremendous attention in forecasting traffic and energy data.
Towards General Robustness to Bad Training Data
In this paper, we focus on the problem of identifying bad training data when the underlying cause is unknown in advance.
Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems
Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity.
Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
While the generative attribute regression module allows us to capture the anomalies in the attribute space, the multi-view contrastive learning module can exploit richer structure information from multiple subgraphs, thus abling to capture the anomalies in the structure space, mixing of structure, and attribute information.
MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition
Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation.
A Unified Framework for Task-Driven Data Quality Management
High-quality data is critical to train performant Machine Learning (ML) models, highlighting the importance of Data Quality Management (DQM).
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
To overcome this problem, inspired by the recent success of graph contrastive learning and Siamese networks in visual representation learning, we propose a novel self-supervised approach in this paper to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning.
Controlling Smart Inverters using Proxies: A Chance-Constrained DNN-based Approach
The trained DNNs can be driven by partial, noisy, or proxy descriptors of the current grid conditions.
Graph Self-Supervised Learning: A Survey
Deep learning on graphs has attracted significant interests recently.
Unitary Approximate Message Passing for Sparse Bayesian Learning
Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm.
Imitation Learning with Stability and Safety Guarantees
A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL).
Power up! Robust Graph Convolutional Network based on Graph Powering
By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.
Power up! Robust Graph Convolutional Network via Graph Powering
By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.
Stability-certified reinforcement learning: A control-theoretic perspective
We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems.
Inverse Reinforcement Learning via Deep Gaussian Process
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations.
Environmental Sensing by Wearable Device for Indoor Activity and Location Estimation
We present results from a set of experiments in this pilot study to investigate the causal influence of user activity on various environmental parameters monitored by occupant carried multi-purpose sensors.
